{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_agxbds3wat5f","handle":"cerberus-mcp","url":"https://wellknown.network/agents/cerberus-mcp","links":{"self":"https://wellknown.network/agents/cerberus-mcp/record.json","html":"https://wellknown.network/agents/cerberus-mcp","markdown":"https://wellknown.network/agents/cerberus-mcp/record.md","api":"https://wellknown.network/api/v1/agents/cerberus-mcp","status":"https://wellknown.network/api/v1/agents/cerberus-mcp/status","claim":"https://wellknown.network/agents/cerberus-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/cerberus-mcp/claim.json","badge":"https://wellknown.network/agents/cerberus-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:cerberus-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"cerberus-mcp","summary":"MCP server instrumentation for Cerberus API monitoring","description":"# cerberus-mcp\n\nMCP (Model Context Protocol) server instrumentation for [Cerberus](https://github.com/gpotrock/cerberus) API monitoring.\n\nDrop-in replacement for `FastMCP` that captures tool, resource, and prompt call metrics and streams them to the Cerberus analytics pipeline.\n\n## Installation\n\n```bash\npip install cerberus-mcp\n```\n\n## Quick Start\n\nReplace `FastMCP` with `CerberusMCP` — a single-line change:\n\n```python\nfrom cerberus_mcp import CerberusMCP\n\nmcp = CerberusMCP(\n    \"my-server\",\n    cerberus_config={\n        \"token\": \"your-api-key\",\n        \"client_id\": \"your-client-id\",\n        \"ws_url\": \"wss://your-cerberus-backend:8765\",\n    }\n)\n\n@mcp.tool()\ndef get_weather(location: str) -> str:\n    \"\"\"Get weather for a location.\"\"\"\n    return f\"Sunny in {location}\"\n\n@mcp.resource(\"config://settings\")\ndef get_settings() -> str:\n    \"\"\"Return server settings.\"\"\"\n    return '{\"theme\": \"dark\"}'\n\n@mcp.prompt()\ndef summarize(text: str) -> str:\n    \"\"\"Summarize text.\"\"\"\n    return f\"Please summarize: {text}\"\n```\n\nAll tool calls, resource reads, and prompt invocations are automatically captured with:\n- Execution timing (duration_ms)\n- Sanitized arguments (sensitive values redacted)\n- Error tracking\n- Result summaries\n- MCP client identity (name, version) and session correlation\n\nEvents are sent asynchronously via WebSocket to the Cerberus event_ingest backend using the same pipeline as `cerberus-django`.\n\n## Configuration\n\n| Key | Required | Description |\n|-----|----------|-------------|\n| `token` | Yes | API key for Cerberus authentication |\n| `client_id` | Yes | Client identifier for your MCP server |\n| `ws_url` | Yes | WebSocket URL of your Cerberus event_ingest server |\n| `server_name` | No | Override server name in events (defaults to MCP server name) |\n\nSet `CERBERUS_DEBUG=true` to enable verbose logging.\n\n## How It Works\n\n`CerberusMCP` subclasses `FastMCP` from the MCP Python SDK and wraps the `tool()`, `resource()`, and `prompt()` decorators. Each handler call is …","publisher":{"name":"Griffin Potrock","url":null},"homepage":"https://github.com/gpotrock/cerberus#mcp-server-monitoring","repository":"https://github.com/gpotrock/cerberus#mcp-server-monitoring","version":"0.1.4","license":null,"protocols":["mcp"],"tags":["ai","analytics","async","instrumentation","llm","mcp","model-context-protocol","monitoring","websocket"],"pricing":null,"endpoints":[{"url":"pypi:cerberus-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.monitoring","name":"Monitoring & Observability","confidence":1,"provenance":"declared"},{"slug":"security.identity","name":"Identity & Access","confidence":0.871,"provenance":"derived"}],"categories":["dev","security"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"cerberus-mcp","registry":"pypi","observedAt":"2026-09-09T11:33:16.467Z","publishedAt":"2026-03-11T06:19:04.744060Z","latestVersion":"0.1.4"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"cerberus-mcp","url":"https://pypi.org/project/cerberus-mcp/","firstSeenAt":"2026-09-09T11:29:59.056Z","fetchedAt":"2026-09-09T11:29:59.056Z","normalizedAt":"2026-09-09T11:29:59.056Z"}]},"firstSeenAt":"2026-09-09T11:29:59.056Z","updatedAt":"2026-09-09T11:33:16.467Z"}